Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–225 of 403 papers

Title	Date	Tasks	Status
MGE: A Training-Free and Efficient Model Generation and Enhancement Scheme	Feb 27, 2024	Adversarial Defense	—Unverified
MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense	Nov 20, 2018	Adversarial Defense	—Unverified
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking	Dec 16, 2019	Adversarial DefenseAnomaly Detection	—Unverified
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models	Jun 13, 2024	Adversarial Defenseimage-classification	—Unverified
Modeling Adversarial Noise for Adversarial Defense	Sep 29, 2021	Adversarial Defense	—Unverified
Multi-head Uncertainty Inference for Adversarial Attack Detection	Dec 20, 2022	Adversarial AttackAdversarial Attack Detection	—Unverified
On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense	Jan 9, 2023	Adversarial AttackAdversarial Defense	—Unverified
Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense	Mar 21, 2023	Adversarial AttackAdversarial Defense	—Unverified
Perceptual Adversarial Robustness: Generalizable Defenses Against Unforeseen Threat Models	Jan 1, 2021	Adversarial DefenseAdversarial Robustness	—Unverified
Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networks	Oct 16, 2024	Adversarial DefenseGraph Neural Network	—Unverified
Physically Realizable Adversarial Examples for LiDAR Object Detection	Apr 1, 2020	Adversarial DefenseAutonomous Driving	—Unverified
Pixel Redrawn For A Robust Adversarial Defense	May 1, 2019	Adversarial Defense	—Unverified
Privacy-preserving Universal Adversarial Defense for Black-box Models	Aug 20, 2024	Adversarial DefenseAutonomous Driving	—Unverified
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images	Dec 11, 2024	Adversarial Defensebackdoor defense	—Unverified
PuVAE: A Variational Autoencoder to Purify Adversarial Examples	Mar 2, 2019	Adversarial DefenseAdversarial Defense against FGSM Attack	—Unverified
RAILS: A Robust Adversarial Immune-inspired Learning System	Dec 18, 2020	Adversarial DefenseDiversity	—Unverified
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples	May 6, 2023	Adversarial AttackAdversarial Defense	—Unverified
Rebuild and Ensemble: Exploring Defense Against Text Adversaries	Nov 16, 2021	Adversarial Defense	—Unverified
Text Adversarial Purification as Defense against Adversarial Attacks	Mar 27, 2022	Adversarial AttackAdversarial Defense	—Unverified
Releasing Inequality Phenomena in L_-Adversarial Training via Input Gradient Distillation	May 16, 2023	Adversarial DefenseAdversarial Robustness	—Unverified
Revisiting and Advancing Adversarial Training Through A Simple Baseline	Jun 13, 2023	Adversarial DefenseAdversarial Robustness	—Unverified
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off	Feb 22, 2024	Adversarial DefenseKnowledge Distillation	—Unverified
Rethinking Textual Adversarial Defense for Pre-trained Language Models	Jul 21, 2022	Adversarial AttackAdversarial Defense	—Unverified
Revisiting Role of Autoencoders in Adversarial Settings	May 21, 2020	Adversarial DefenseAdversarial Robustness	—Unverified
Robust Adversarial Defense by Tensor Factorization	Sep 3, 2023	Adversarial Defense	—Unverified

Show:10 25 50

← PrevPage 9 of 17Next →

All datasets CIFAR-10 ImageNet (non-targeted PGD, max perturbation=4)ImageNet ImageNet (targeted PGD, max perturbation=16)MNIST CAAD 2018 miniImageNet

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	WRN-28-10	Accuracy	90.03	—	Unverified
2	Diffusion Classifier	Accuracy	89.85	—	Unverified
3	Stochastic-LWTA/PGD/WideResNet-34-10	Accuracy	84.3	—	Unverified
4	Ours (Stochastic-LWTA/PGD/WideResNet-34-5)	Accuracy	83.4	—	Unverified
5	Ours (Stochastic-LWTA/PGD/WideResNet-34-1)	Accuracy	81.87	—	Unverified
6	ResNet18 (TRADES-ANCRA/PGD-40)	Accuracy	81.7	—	Unverified
7	Stochastic-LWTA/PGD/WideResNet-34-5	Attack: AutoAttack	81.22	—	Unverified
8	PCL (against PGD, white box)	Accuracy	46.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SAT-EfficientNet-L1	Accuracy	58.6	—	Unverified
2	LLR-ResNet-152	Accuracy	47	—	Unverified
3	ResNet-152 free-m=4	Accuracy	36	—	Unverified
4	ResNet-101 free-m=4	Accuracy	34.3	—	Unverified
5	ResNet-50 free-m=4	Accuracy	31.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet101	Accuracy	99.8	—	Unverified
2	InceptionV3	Accuracy	98.6	—	Unverified
3	Feature Denoising	Accuracy	49.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-152 Denoise	Accuracy	42.8	—	Unverified
2	ResNeXt-101 DenoiseAll	Accuracy	40.4	—	Unverified
3	ResNet-152	Accuracy	39	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Defense GAN	Accuracy	0.85	—	Unverified
2	PuVAE	Accuracy	0.81	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Feature Denoising	Accuracy	50.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Auto Encoder-Block Switching defense with GradCAM	Accuracy	88.54	—	Unverified